An agent that preps the room before you walk in

I run AI enablement workshops, and I always wanted to know what the people in the room needed from AI before I walked in. So I built an agent the participants email before the workshop — it collects what they want AI to do, explains what AI can and can't do for their task, coaches them through getting it working, and hands me a briefing built out of real, named pain points the participants already own.

What this could do for your organization

If you want to equip your team, your department, or your whole organization to use AI in their actual work — without the hype, the confusion, or a compliance misstep — I run AI enablement workshops for that. What makes my workshop different is the pre-session email agent: each participant engages with it in the week before we meet, describes their real task, gets an honest read of where AI can and can't help, and gets coached through actually trying something. By the time I walk into the room, the skeptics have already had a working AI exchange on something real, and I have a briefing built out of specific pain points rather than a generic agenda.

If you already run workshops yourself — you're an OD lead, an HR director, a facilitator, a training company — the same agent can be customized for your sessions. Your branding, your inbox, your voice, tuned to your organization's specifics. Participants engage with your agent in the week before your session; you walk in with a facilitator briefing built from real pain points in that specific room; and for a series of sessions the agent opens each follow-up the way a colleague would — without the "as a language model I don't remember" problem.

Either way, the agent does its homework on your organization up front: data privacy rules (Law 25 in Quebec, GDPR or PIPEDA elsewhere), your corporate policy on what can and can't be uploaded, the document types your team actually works with. When a participant asks "can I put this into ChatGPT," the agent already knows your answer — before the session, not during the Q&A.

What your team gets back

If I'm running the workshop for you, you get the session itself — half-day, full-day, or multi-day, in English or Quebec French, sized to your team, department, or organization — and every participant also gets a week of guided pre-engagement with the agent in the days before. The agent knows your organization's AI policy, your Law 25 posture, and the document types your team works with, so the compliance Q&A gets answered before the session instead of during it. The morning of the workshop, I have a briefing built out of the specific pain points your specific people raised — which is the agenda.

If you're running the workshops yourself, you get your own branded agent — your own inbox, your own voice, your own knowledge of your organization's Law 25 posture and corporate AI policy. Every workshop you run becomes two things: a pre-session email loop where participants bring real tasks and get coached through them, and a facilitator briefing built out of named pain points, delivered to the person running the session the morning of. The first engagement is the standup — I build your agent, tune it to your organization, your brand voice in both languages. After that it runs in the background, one engagement per session, with you controlling the handoff.

How I did it

The email is the interface on purpose. Participants write in their own words about their own task, and the agent writes back with a specific, honest read — what AI can do well for them, what it can't. By the time I walk into the room, most of the skeptics have already had a working exchange with AI on something real.

The agent reads a participant's task and responds with an honest assessment — AI is strong at these parts, not so good at others. No hype, no "AI can do everything."

When someone's task is something AI can help with, the agent offers to coach them through getting it working. Three exchanges later, the skeptic walks into the room already winning.

A week later, the agent opens the next conversation like a colleague who was paying attention — no re-explaining, no "as a language model I don't remember."

Morning of the workshop, I get a briefing built out of real, named pain points — not a generic agenda that could have been written last year.

Before the first email goes out, the agent researches the organization's document types and decides ahead of time how each should be handled — data privacy under Law 25, corporate policy on what can and can't go to a cloud AI. When a participant asks about something that touches either one, the agent already knows the answer.

The reusable part is the pattern — an agent that learns in the spaces between formal interactions, and hands its learning to the facilitator instead of hiding it in a dashboard nobody checks. The architecture is designed so a new client gets their own agent, their own inbox, their own branding, and their own tuned knowledge base. Quebec French or English, bilingual if that's what you need.

If you run workshops, offsites, or training sessions and you want the agenda to write itself out of what your people are actually stuck on, drop me a line. I'll show you what the agent already knows about a problem you bring to it.

Let's talk →

Related projects

Eighteen years of email, turned into a pattern library

Another agent learning from a corpus of real conversations, in a different domain.

Read the story →

A CV anonymizer that strips identity before any AI reads it

The Law 25 work the agent coaches participants on — built, shippable, running on Montreal soil.

Read the story →

How I work

I work with my AI and the person who owns the business process — understand the context, select and adapt one of my existing protocols, deliver the results.

Read the page →